Multigradient Siamese Temporal Model for the Prediction of Clinical Events in Rapid Response Systems
- 17 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Systems
- Vol. 39 (6) , 58-69
Abstract
Early identification of emergency situations for intensive care unit (ICU) patients is a critical component of precision medicine. We present a Multi-gradient Siamese Temporal (MG-SiameseTS) model to predict patients’ clinical status within an 8-h window and trigger an alarm when anticipating an emergent situation. It incorporates gradient extractors, contrastive learning, focal loss, and imbalanced loss to address challenges related to bias, data quality, and interpretability. Experimental results using a practical dataset collected from the rapid response team at Chonnam National University Hospital in Korea demonstrate that the MG-SiameseTS model exhibits superior predictive capabilities for clinical events compared to several state-of-the-art methods.Keywords
Funding Information
- Ministry of Science and Information Technology (RS-2023-00219107)
- Institute of Information and Communications Technology Planning and Evaluation (IITP-2023-RS-2023-00256629)
- Chonnam National University Hwasun Hospital (HCRI23001)
This publication has 18 references indexed in Scilit:
- A sliding window approach to optimize the time-varying parameters of a spatially-explicit and stochastic model of COVID-19PLOS Global Public Health, 2022
- Mixing up contrastive learning: Self-supervised representation learning for time seriesPattern Recognition Letters, 2022
- Major challenges and barriers in clinical decision-making as perceived by emergency medical services personnel: a qualitative content analysisBMC Emergency Medicine, 2021
- Temporal convolutional networks allow early prediction of events in critical careJournal of the American Medical Informatics Association, 2019
- Deep Interpretable Early Warning System for the Detection of Clinical DeteriorationIEEE Journal of Biomedical and Health Informatics, 2019
- An Algorithm Based on Deep Learning for Predicting In‐Hospital Cardiac ArrestJournal of the American Heart Association, 2018
- National Early Warning Score (NEWS) at ICU discharge can predict early clinical deterioration after ICU transferJournal of Critical Care, 2018
- Serious adverse events in a hospital using early warning score – What went wrong?Resuscitation, 2014
- Intensive care unit scoring systems outperform emergency department scoring systems for mortality prediction in critically ill patients: a prospective cohort studyJournal of Intensive Care, 2014
- Early Identification of Patients at Risk for Difficult Intubation in the Intensive Care UnitAmerican Journal of Respiratory and Critical Care Medicine, 2013